@inproceedings{li-etal-2022-hw,
title = "{HW}-{TSC}{'}s Participation in the {IWSLT} 2022 Isometric Spoken Language Translation",
author = "Li, Zongyao and
Guo, Jiaxin and
Wei, Daimeng and
Shang, Hengchao and
Wang, Minghan and
Zhu, Ting and
Wu, Zhanglin and
Yu, Zhengzhe and
Chen, Xiaoyu and
Lei, Lizhi and
Yang, Hao and
Qin, Ying",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Costa-juss{\`a}, Marta",
booktitle = "Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)",
month = may,
year = "2022",
address = "Dublin, Ireland (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.iwslt-1.33",
doi = "10.18653/v1/2022.iwslt-1.33",
pages = "361--368",
abstract = "This paper presents our submissions to the IWSLT 2022 Isometric Spoken Language Translation task. We participate in all three language pairs (English-German, English-French, English-Spanish) under the constrained setting, and submit an English-German result under the unconstrained setting. We use the standard Transformer model as the baseline and obtain the best performance via one of its variants that shares the decoder input and output embedding. We perform detailed pre-processing and filtering on the provided bilingual data. Several strategies are used to train our models, such as Multilingual Translation, Back Translation, Forward Translation, R-Drop, Average Checkpoint, and Ensemble. We investigate three methods for biasing the output length: i) conditioning the output to a given target-source length-ratio class; ii) enriching the transformer positional embedding with length information and iii) length control decoding for non-autoregressive translation etc. Our submissions achieve 30.7, 41.6 and 36.7 BLEU respectively on the tst-COMMON test sets for English-German, English-French, English-Spanish tasks and 100{\%} comply with the length requirements.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2022-hw">
<titleInfo>
<title>HW-TSC’s Participation in the IWSLT 2022 Isometric Spoken Language Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zongyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daimeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengchao</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhanglin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengzhe</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizhi</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents our submissions to the IWSLT 2022 Isometric Spoken Language Translation task. We participate in all three language pairs (English-German, English-French, English-Spanish) under the constrained setting, and submit an English-German result under the unconstrained setting. We use the standard Transformer model as the baseline and obtain the best performance via one of its variants that shares the decoder input and output embedding. We perform detailed pre-processing and filtering on the provided bilingual data. Several strategies are used to train our models, such as Multilingual Translation, Back Translation, Forward Translation, R-Drop, Average Checkpoint, and Ensemble. We investigate three methods for biasing the output length: i) conditioning the output to a given target-source length-ratio class; ii) enriching the transformer positional embedding with length information and iii) length control decoding for non-autoregressive translation etc. Our submissions achieve 30.7, 41.6 and 36.7 BLEU respectively on the tst-COMMON test sets for English-German, English-French, English-Spanish tasks and 100% comply with the length requirements.</abstract>
<identifier type="citekey">li-etal-2022-hw</identifier>
<identifier type="doi">10.18653/v1/2022.iwslt-1.33</identifier>
<location>
<url>https://aclanthology.org/2022.iwslt-1.33</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>361</start>
<end>368</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HW-TSC’s Participation in the IWSLT 2022 Isometric Spoken Language Translation
%A Li, Zongyao
%A Guo, Jiaxin
%A Wei, Daimeng
%A Shang, Hengchao
%A Wang, Minghan
%A Zhu, Ting
%A Wu, Zhanglin
%A Yu, Zhengzhe
%A Chen, Xiaoyu
%A Lei, Lizhi
%A Yang, Hao
%A Qin, Ying
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Costa-jussà, Marta
%S Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland (in-person and online)
%F li-etal-2022-hw
%X This paper presents our submissions to the IWSLT 2022 Isometric Spoken Language Translation task. We participate in all three language pairs (English-German, English-French, English-Spanish) under the constrained setting, and submit an English-German result under the unconstrained setting. We use the standard Transformer model as the baseline and obtain the best performance via one of its variants that shares the decoder input and output embedding. We perform detailed pre-processing and filtering on the provided bilingual data. Several strategies are used to train our models, such as Multilingual Translation, Back Translation, Forward Translation, R-Drop, Average Checkpoint, and Ensemble. We investigate three methods for biasing the output length: i) conditioning the output to a given target-source length-ratio class; ii) enriching the transformer positional embedding with length information and iii) length control decoding for non-autoregressive translation etc. Our submissions achieve 30.7, 41.6 and 36.7 BLEU respectively on the tst-COMMON test sets for English-German, English-French, English-Spanish tasks and 100% comply with the length requirements.
%R 10.18653/v1/2022.iwslt-1.33
%U https://aclanthology.org/2022.iwslt-1.33
%U https://doi.org/10.18653/v1/2022.iwslt-1.33
%P 361-368
Markdown (Informal)
[HW-TSC’s Participation in the IWSLT 2022 Isometric Spoken Language Translation](https://aclanthology.org/2022.iwslt-1.33) (Li et al., IWSLT 2022)
ACL
- Zongyao Li, Jiaxin Guo, Daimeng Wei, Hengchao Shang, Minghan Wang, Ting Zhu, Zhanglin Wu, Zhengzhe Yu, Xiaoyu Chen, Lizhi Lei, Hao Yang, and Ying Qin. 2022. HW-TSC’s Participation in the IWSLT 2022 Isometric Spoken Language Translation. In Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pages 361–368, Dublin, Ireland (in-person and online). Association for Computational Linguistics.